© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15766
    Prev
    Next
    INDEX
    Explanations

    excessive punctuation and separators

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on long runs of the same punctuation character (e.g. sequences of dots, underscores, etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    獁
    -2.36
    𖡼
    -1.95
     台灣
    -1.90
     市場
    -1.89
     anún
    -1.88
     咖啡
    -1.84
    塒
    -1.83
    壜
    -1.81
     來
    -1.80
     nuest
    -1.79
    POSITIVE LOGITS
     a
    1.91
    ?”
    1.84
     to
    1.82
    ↵
    1.70
     of
    1.70
     (“
    1.65
     ’
    1.63
     are
    1.60
     wasn
    1.60
     jefes
    1.59
    Activations Density 0.017%

    No Known Activations